INDEX

Explanations

code snippets/questions

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

çħĮ

-0.27

 correct

-0.26

emption

-0.25

Pear

-0.24

Highlighted

-0.24

"People

-0.24

æ±Ĺ

-0.24

munition

-0.24

issan

-0.24

æĸ°éĹ»ç½ĳ

-0.24

POSITIVE LOGITS

 trá»¥

0.29

uÃŃ

0.26

dt

0.25

 proph

0.25

/--

0.25

è³ŀ

0.25

é£İåĲ¹

0.25

 portion

0.24

/-

0.24

odesk

0.24

Activations Density 0.000%

code snippets/questions

No Comments

No Known Activations